Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comparing, role, Q, background

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitVars
    -0.52
    WritableDatabase
    -0.50
    UnsafeEnabled
    -0.50
    ASX
    -0.48
     defaultdict
    -0.48
     Infórmanos
    -0.47
    brio
    -0.47
    άνι
    -0.47
    wikipedia
    -0.46
    annica
    -0.45
    POSITIVE LOGITS
    Personensuche
    0.81
    confirmPassword
    0.71
    IndentedString
    0.65
    equalTo
    0.64
    identical
    0.64
    HomeAsUpEnabled
    0.61
    enterOuterAlt
    0.60
    Confirm
    0.60
    espejo
    0.60
     identically
    0.59
    Act Density 0.004%

    No Known Activations